Joint A* CCG Parsing and Semantic Role Labelling

Lewis, Mike; He, Luheng; Zettlemoyer, Luke

doi:10.18653/v1/d15-1169

Cited by 42 publications

(43 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To realize this vision in practice, an approach is needed to build a CCG parser enriched with graph semantics for deriving AMRs. We anticipate that existing CCG parsing frameworks can be adapted-for example, by developing an alignment algorithm to induce the semantics for lexical entries from the AMR corpus, and running an off-the-shelf parser like EasySRL (Lewis et al, 2015) at training and test time for the syntactic side of the derivation. This approach would take advantage of the fact that our analysis assumes the ordinary CCG syntax for obtaining the compositional structure of the derivation.…”

Section: Discussionmentioning

confidence: 99%

An Improved Approach for Semantic Graph Composition with CCG

Blodgett¹,

Schneider²

2019

Proceedings of the 13th International Conference on Computational Semantics - Long Papers

View full text Add to dashboard Cite

This paper builds on previous work using Combinatory Categorial Grammar (CCG) to derive a transparent syntax-semantics interface for Abstract Meaning Representation (AMR) parsing. We define new semantics for the CCG combinators that is better suited to deriving AMR graphs. In particular, we define relation-wise alternatives for the application and composition combinators: these require that the two constituents being combined overlap in one AMR relation. We also provide a new semantics for type raising, which is necessary for certain constructions. Using these mechanisms, we suggest an analysis of eventive nouns, which present a challenge for deriving AMR graphs. Our theoretical analysis will facilitate future work on robust and transparent AMR parsing using CCG.

show abstract

Section: Discussionmentioning

confidence: 99%

An Improved Approach for Semantic Graph Composition with CCG

Blodgett¹,

Schneider²

2019

Proceedings of the 13th International Conference on Computational Semantics - Long Papers

View full text Add to dashboard Cite

show abstract

“…More ambitiously, the annotation has the potential to be used for training parsers. A joint syntactic and semantic parser, such as that of Lewis et al (2015), could be trained directly on the annotations to improve both the syntactic and semantic models, for example in domain transfer settings. Alternatively, the annotation could be used for active learning: we envisage a scheme where parsers, when faced with ambiguous attachment decisions, can generate a human-readable question whose answer will resolve the attachment.…”

Section: Discussion and Future Workmentioning

confidence: 99%

Question-Answer Driven Semantic Role Labeling: Using Natural Language to Annotate Natural Language

He¹,

Lewis²,

Zettlemoyer³

2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

Self Cite

169

178

View full text Add to dashboard Cite

This paper introduces the task of questionanswer driven semantic role labeling (QA-SRL), where question-answer pairs are used to represent predicate-argument structure. For example, the verb "introduce" in the previous sentence would be labeled with the questions "What is introduced?", and "What introduces something?", each paired with the phrase from the sentence that gives the correct answer. Posing the problem this way allows the questions themselves to define the set of possible roles, without the need for predefined frame or thematic role ontologies. It also allows for scalable data collection by annotators with very little training and no linguistic expertise. We gather data in two domains, newswire text and Wikipedia articles, and introduce simple classifierbased models for predicting which questions to ask and what their answers should be. Our results show that non-expert annotators can produce high quality QA-SRL data, and also establish baseline performance levels for future work on this task.

show abstract

“…Joint learning in NLP pipelines. To avoid cascading errors, much effort has been devoted to joint decoding in NLP pipelines (Habash and Rambow, 2005;Cohen and Smith, 2007;Goldberg and Tsarfaty, 2008;Lewis et al, 2015;Zhang et al, 2015, inter alia). However, joint inference can sometimes be prohibitively expensive.…”

Section: Related Workmentioning

confidence: 99%

Backpropagating through Structured Argmax using a SPIGOT

Peng

Thomson

Smith

2018

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

We introduce the structured projection of intermediate gradients optimization technique (SPIGOT), a new method for backpropagating through neural networks that include hard-decision structured predictions (e.g., parsing) in intermediate layers. SPIGOT requires no marginal inference, unlike structured attention networks (Kim et al., 2017) and some reinforcement learning-inspired solutions (Yogatama et al., 2017). Like socalled straight-through estimators (Hinton, 2012), SPIGOT defines gradient-like quantities associated with intermediate nondifferentiable operations, allowing backpropagation before and after them; SPIGOT's proxy aims to ensure that, after a parameter update, the intermediate structure will remain well-formed.We experiment on two structured NLP pipelines: syntactic-then-semantic dependency parsing, and semantic parsing followed by sentiment classification. We show that training with SPIGOT leads to a larger improvement on the downstream task than a modularly-trained pipeline, the straight-through estimator, and structured attention, reaching a new state of the art on semantic dependency parsing.

show abstract

Joint A* CCG Parsing and Semantic Role Labelling

Cited by 42 publications

References 37 publications

An Improved Approach for Semantic Graph Composition with CCG

An Improved Approach for Semantic Graph Composition with CCG

Question-Answer Driven Semantic Role Labeling: Using Natural Language to Annotate Natural Language

Backpropagating through Structured Argmax using a SPIGOT

Contact Info

Product

Resources

About